OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Research Agents

Deep Research MCP Server

Deep Research MCP Server is a TypeScript developer tool that connects a Gemini-powered research agent to MCP-compatible clients and offers a standalone command-line interface. It iteratively explores a query and generates a structured Markdown report.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Deep Research MCP Server — OpenViST project profile in Research Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you can provide a Gemini API key and want research either as an MCP tool or through the standalone CLI.

Who it is for

  • Developers adding research-agent functionality to MCP-compatible clients.
  • Users who want to run a Gemini-based research query from a command line.

Documented uses

  • Investigate a topic through iterative search-query generation and result analysis.
  • Adjust research depth and breadth, or pass existing learnings as context.
  • Produce a structured Markdown report with methodology, limitations, key learnings and references.
Before you choose

Requirements & limits

  • Requires Node.js v22.x and a Google Gemini API key.
  • Google Search Grounding, code execution and function calling are configurable through environment flags.
  • The repository identifies the project as MIT-licensed.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the server for MCP use

Prepare the project and start its MCP server for an MCP-compatible client.

Before you start

  • Node.js v22.x
  • A Google Gemini API key
  • An MCP-compatible client

Steps

  1. Clone the repository and install its dependencies with npm install.

  2. Create .env.local in the project root and set GEMINI_API_KEY.

  3. Build the project with npm run build.

  4. Start the server with node --env-file .env.local dist/mcp-server.js.

Expected outcome

The MCP server process is started and can be invoked by an MCP-compatible client.

Guide limitations

  • The instructions do not include client-specific configuration steps.
Documentation 1 ↗
Source-based practical guide

Run a research query from the command line

Submit a research query through the documented standalone CLI.

Before you start

  • Node.js v22.x
  • A Google Gemini API key configured for the project

Steps

  1. Follow the README setup steps to install dependencies and configure .env.local.

  2. Run npm run start "your research query".

Expected outcome

The CLI is used to submit a research query.

Guide limitations

  • The provided CLI example does not specify output options or additional query controls.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
ssdeanx/deep-research-mcp-server · Official homepage title · retained in its source language
How we review sourcesSuggest a correction